Skip to main navigation Skip to search Skip to main content

A Fast Multiscale Spatial Regularization for Sparse Hyperspectral Unmixing

  • Ricardo Augusto Borsoi
  • , Tales Imbiriba
  • , Jose Carlos Moreira Bermudez
  • , Cedric Richard
  • Universidade Federal de Santa Catarina
  • Universite Cote d'Azur

Research output: Contribution to journal › Article › peer-review

Abstract

Sparse hyperspectral unmixing from large spectral libraries has been considered to circumvent the limitations of endmember extraction algorithms in many applications. This strategy often leads to ill-posed inverse problems, which can greatly benefit from spatial regularization strategies. However, existing spatial regularization strategies lead to large-scale nonsmooth optimization problems. Thus, efficiently introducing spatial context in the unmixing problem remains a challenge and a necessity for many real world applications. In this letter, a novel multiscale spatial regularization approach for sparse unmixing is proposed. The method uses a signal-adaptive spatial multiscale decomposition based on segmentation and oversegmentation algorithms to decompose the unmixing problem into two simpler problems: one in an approximation image domain and another in the original domain. Simulation results using both synthetic and real data indicate that the proposed method outperforms the state-of-the-art total variation-based algorithms with a computation time comparable to that of their unregularized counterparts.

Original languageEnglish
Article number8536490
Pages (from-to)598-602
Number of pages5
JournalIEEE Geoscience and Remote Sensing Letters
Volume16
Issue number4
DOIs
StatePublished - Apr 2019

ASJC Scopus Subject Areas

  • Geotechnical Engineering and Engineering Geology
  • Electrical and Electronic Engineering

Keywords

  • Hyperspectral data
  • multiscale
  • sparse unmixing
  • spatial regularization
  • superpixels

Fingerprint

Dive into the research topics of 'A Fast Multiscale Spatial Regularization for Sparse Hyperspectral Unmixing'. Together they form a unique fingerprint.

Cite this